Frequency Combs and Deep Learning Enable Fast, High-Fidelity Ghost Imaging
Fast, High-Fidelity Ghost Imaging Merges Frequency Combs and Deep Learning
Topics and contents
Topic
On this page
Ghost imaging replaces pixelated sensors with correlation measurements between structured illumination and a single-pixel detector. Researchers combined an optical frequency comb with deep learning to achieve faster, higher-fidelity ghost imaging.
The original article shows the combination of frequency comb illumination with AI reconstruction, a typical example of optics and AI working together in computational imaging
Ghost imaging, a technique that reframes image formation by replacing pixelated sensors with correlation measurements between structured illumination and a single-pixel detector, offers distinct advantages in low-light settings, through scattering media, and on platforms where hardware size is limited. But while, in theory, ghost imaging provides a satisfactory solution to capturing images in photon-starved or size-constrained environments, in practice, it has been of limited use. Conventional ghost imaging is fundamentally slow, because it typically uses spatial light modulators or swept-frequency lasers to generate uncorrelated, 2D illumination patterns and project them onto the target sequentially. The use of slow,...
Source: Photonics.com · photonics.com